Simple Does It: Weakly Supervised Instance and Semantic Segmentation

Abstract

Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annotations, we propose a new approach that does not require modification of the segmentation training procedure. We show that when carefully designing the input labels from given bounding boxes, even a single round of training is enough to improve over previously reported weakly supervised results. Overall, our weak supervision approach reaches ~95% of the quality of the fully supervised model, both for semantic labelling and instance segmentation.

References in corpus (18)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Multi-Scale Context Aggregation by Dilated Convolutions
• What makes for effective detection proposals?
• Learning to Segment Object Candidates
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
• Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
• Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
• Fully Convolutional Multi-Class Multiple Instance Learning
• Simultaneous Detection and Segmentation
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
• What's the Point: Semantic Segmentation with Point Supervision
• Deep Interactive Object Selection
• LooseCut: Interactive Image Segmentation with Loosely Bounded Boxes
• The Fast Bilateral Solver
• Weakly Supervised Object Boundaries

Cited by in corpus (11)

• Gaussian Dynamic Convolution for Efficient Single-Image Segmentation
• Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation
• Exploiting saliency for object segmentation from image level labels
• Effective Use of Synthetic Data for Urban Scene Semantic Segmentation
• Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label
• Signet Ring Cell Detection With a Semi-supervised Learning Framework
• BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansion
• Panoptic One-Click Segmentation: Applied to Agricultural Data
• Discovering Latent Classes for Semi-Supervised Semantic Segmentation
• Diverse Sampling for Self-Supervised Learning of Semantic Segmentation
• Weakly-Supervised Cell Tracking via Backward-and-Forward Propagation